The Returning Farmland to Forest Program (RFFP) is widely known as one of China’s largest and most successful payment schemes for ecosystem service projects for the achievement of both environmental and economic sustainability. By sponsoring afforestation activities and compensating farmers for converting cropland to forest, the project was designed to achieve multiple goals. Ecologically, the program aims to expand forest cover and to reduce flood and soil erosion. Economically, it aims to alleviate poverty and improve rural livelihoods. Although the official metrics indicate successful program outcomes in the short term, researchers have reported mixed and controversial results for long-term outcomes. We combined the difference-in-difference (DID) with instrumental variables (IVs) regression to examine the long-term effects of China’s RFFP on local economic development. We found that (1) the RFFP has had a remarkably positive impact on local economic growth in the primary sector, but considerably limits the growth of enterprises above a designated size by 16.8%; (2) the RFFP is unable to promote the development of the secondary industry because it cannot effectively promote the transfer of rural laborers to the secondary industry sector; and (3) in addition to increasing the general budgetary expenditure of local finance by 7.50%, this program has significantly reduced local fiscal revenue by 35.50%. We suggest that eco-compensation should consider the performance of the RFFP in its evaluation criteria.

From an ecosystem perspective, mergers and acquisitions (M&A) are one of the key paths for firms to foster complementary sectors and gain complementary assets. From the perspective of sustainable development, M&A can reallocate resources from target to asset to achieve better synergy and prolong the operation of a merged firm. However, M&A activities are characterized by high risk due to the high cost and uncertainty. Thus, a prediction model of M&A decisions is valuable for firms’ strategy design from an ecosystem and sustainable development perspective. By adopting a machine learning technique, this study measured the cross-border M&A decisions by analyzing firm-level cross-sectional data of the global financial marketplace under ecosystem mapping for the application of various country, deal and firm-level indicators related to sustainable development. Our paper can support the hypotheses of corporate governance, ecosystem stakeholder theory, ecosystem risk and institution theory in explaining that firms can increase their success rate of M&A to achieve sustainable development. Methodologically, we used AdaBoost to train several weak classifiers (decision trees) to achieve a strong decision-making model with a large financial transaction database of 215,160 deal activities. Results achieved 80.1% prediction accuracy by using the AdaBoost model through 10-fold cross validation. We found that differences exist on prediction features of M&A with different characteristics of sustainable development. For a robustness check, comparable results were obtained with a support vector machine (SVM) model. By analyses of the features during the cross-border M&A decision-making processing, this study is expected to contribute to the utilization of machine learning in ecosystem studies.